Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    full and what follows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    v
    0.72
    "]:
    0.60
    g
    0.58
    d
    0.57
    b
    0.56
    N
    0.56
    et
    0.54
     alguns
    0.54
    r
    0.54
    fixed
    0.52
    POSITIVE LOGITS
     full
    1.32
     FULL
    1.25
     Full
    1.14
    完整的
    1.12
     fully
    1.09
     volled
    1.08
    完整
    1.05
    Full
    1.03
     كامل
    1.03
     completo
    1.02
    Act Density 0.062%

    No Known Activations